| #------------------------------------------------------------- |
| # |
| # Licensed to the Apache Software Foundation (ASF) under one |
| # or more contributor license agreements. See the NOTICE file |
| # distributed with this work for additional information |
| # regarding copyright ownership. The ASF licenses this file |
| # to you under the Apache License, Version 2.0 (the |
| # "License"); you may not use this file except in compliance |
| # with the License. You may obtain a copy of the License at |
| # |
| # http://www.apache.org/licenses/LICENSE-2.0 |
| # |
| # Unless required by applicable law or agreed to in writing, |
| # software distributed under the License is distributed on an |
| # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| # KIND, either express or implied. See the License for the |
| # specific language governing permissions and limitations |
| # under the License. |
| # |
| #------------------------------------------------------------- |
| |
| /* |
| * The MNIST Data can be downloaded as follows: |
| * mkdir -p data/mnist/ |
| * cd data/mnist/ |
| * curl -O https://pjreddie.com/media/files/mnist_train.csv |
| * curl -O https://pjreddie.com/media/files/mnist_test.csv |
| */ |
| |
| source("nn/examples/mnist_softmax.dml") as mnist_softmax |
| |
| # Read training data |
| data = read("mnist_data/mnist_train.csv", format="csv") |
| n = nrow(data) |
| |
| # Extract images and labels |
| images = data[,2:ncol(data)] |
| labels = data[,1] |
| |
| # Scale images to [0,1], and one-hot encode the labels |
| images = images / 255.0 |
| labels = table(seq(1, n), labels+1, n, 10) |
| |
| # Split into training (55,000 examples) and validation (5,000 examples) |
| X = images[5001:nrow(images),] |
| X_val = images[1:5000,] |
| y = labels[5001:nrow(images),] |
| y_val = labels[1:5000,] |
| |
| # Train |
| epochs = 1 |
| [W, b] = mnist_softmax::train(X, y, X_val, y_val, epochs) |
| |
| # Read test data |
| data = read("mnist_data/mnist_test.csv", format="csv") |
| n = nrow(data) |
| |
| # Extract images and labels |
| X_test = data[,2:ncol(data)] |
| y_test = data[,1] |
| |
| # Scale images to [0,1], and one-hot encode the labels |
| X_test = X_test / 255.0 |
| y_test = table(seq(1, n), y_test+1, n, 10) |
| |
| # Eval on test set |
| probs = mnist_softmax::predict(X_test, W, b) |
| [loss, accuracy] = mnist_softmax::eval(probs, y_test) |
| |
| print("Test Accuracy: " + accuracy) |